fix: suppress teardown startup failures

This commit is contained in:
Tianyi Cui
2026-07-14 12:45:12 +08:00
parent 253f707c35
commit b47e4c5276
8 changed files with 14 additions and 9 deletions

View File

@@ -56,7 +56,7 @@ Default loop processing remains exposed through plugin-visible services and even
A **session** is an append-only event log. A **turn** drains queued input until the model stops asking for tools and no plugin requests continuation. A **step** is one model request plus the tool executions caused by that response. In the flow below ([sequence companion](agent-lifecycle.md)), quoted names are durable session events and event names are extension points.
Startup resolves one identity. No id mints `<config-id>-session-<uuid>`; `sessionId` resumes stored or creates; `resumeSessionId` requires history. Failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject buffered work.
Startup resolves identity. No id mints `<config-id>-session-<uuid>`; `sessionId` resumes or creates; `resumeSessionId` requires history. Active failures emit `agent-loop/config-start-failed(sessionId, error)`, so front doors reject work; teardown stays silent.
### Turn Flow

View File

@@ -131,7 +131,7 @@ export interface Config {
Depends on: [`AgentOptions`](../packages/core/agent/src/index.ts) · [`SessionId`](../packages/core/session/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:353`](../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:354`](../packages/core/agent-loop/src/index.ts)
## `@deepseek-ai/dsh-bash-local`

View File

@@ -179,13 +179,13 @@ Source: [`packages/core/agent/src/types.ts:576`](../../packages/core/agent/src/t
### `agent-loop/config-start-failed` — emit
A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever.
A declarative agent entry failed before it could publish a live agent. Consumers that buffer work for the configured identity use this transient signal to reject that work instead of waiting forever. Normal factory teardown suppresses failures from the cancelled startup attempt.
```ts cordis-catalog
'agent-loop/config-start-failed'(sessionId: SessionId, error: unknown): void
```
Source: [`packages/core/agent-loop/src/index.ts:348`](../../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:349`](../../packages/core/agent-loop/src/index.ts)
## `approval/*`

View File

@@ -19,7 +19,7 @@ async createAgent(ownerCtx: Context, options: CreateAgentOptions): Promise<Agent
async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise<AgentHandle>
```
Source: [`packages/core/agent-loop/src/index.ts:368`](../../packages/core/agent-loop/src/index.ts)
Source: [`packages/core/agent-loop/src/index.ts:369`](../../packages/core/agent-loop/src/index.ts)
## `ctx.agents` — `AgentRegistry`

View File

@@ -7,7 +7,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac
| Event | Mode | Declared in | Dispatchers | Listeners |
| --- | --- | --- | --- | --- |
| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:348`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent-loop/config-start-failed` | `emit` | [`packages/core/agent-loop/src/index.ts:349`](../packages/core/agent-loop/src/index.ts) | [`agent-loop`](../packages/core/agent-loop) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) |
| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - |

View File

@@ -41,7 +41,7 @@ interface Config {
}
```
Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. A declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin.
Agents listed in config are auto-created at startup. `cwd` seeds a fresh config-created session; a materialized exact `sessionId` remount and an explicit `resumeSessionId` keep the persisted session header. While the factory is active, a declarative lookup, resume, setup, or publication failure is contained, logged, and emitted as `agent-loop/config-start-failed(sessionId, error)` because no live `Agent` exists for an `agent/*` signal; cancellation caused by factory teardown is silent. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin.
### Exported concrete class

View File

@@ -340,7 +340,8 @@ declare module 'cordis' {
/**
* A declarative agent entry failed before it could publish a live agent.
* Consumers that buffer work for the configured identity use this
* transient signal to reject that work instead of waiting forever.
* transient signal to reject that work instead of waiting forever. Normal
* factory teardown suppresses failures from the cancelled startup attempt.
* @param sessionId - exact shared agent/session identity that failed startup.
* @param error - persistence, setup, or publication failure.
* @mode emit
@@ -431,6 +432,7 @@ export class AgentLoop extends Service implements AgentFactory {
sessionId: SessionId,
error: unknown,
): void {
if (!this.ownership.isActive()) return
this.ctx.logger.warn(`agent "${configId}": config-driven ${action} of "${sessionId}" failed: ${renderThrown(error)}`)
const args: unknown[] = ['agent-loop/config-start-failed', sessionId, error]
for (const callback of this.ctx.events.dispatch('emit', args)) {

View File

@@ -172,6 +172,8 @@ describe('config-driven session id', () => {
const listing = Promise.withResolvers<Awaited<ReturnType<typeof ctx.sessionPersistence.list>>>()
vi.spyOn(ctx.sessionPersistence, 'list').mockReturnValue(listing.promise)
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
const failures: unknown[] = []
ctx.on('agent-loop/config-start-failed', (_sessionId, error) => { failures.push(error) })
const loop = await ctx.plugin(AgentLoop, {
agents: [{ id: 'main', sessionId: SessionId('stdio-exact-dispose'), model: 'mock' }],
@@ -181,9 +183,10 @@ describe('config-driven session id', () => {
await Promise.resolve()
expect(disposed).toBe(false)
listing.resolve([])
listing.reject(new Error('startup cancelled by teardown'))
await disposal
expect(ctx.agents.get(SessionId('stdio-exact-dispose'))).toBeUndefined()
expect(failures).toEqual([])
expect(warn).not.toHaveBeenCalled()
warn.mockRestore()
await ctx.fiber.dispose()